Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,4 @@ turkish-llama-3-8b-function-calling-q2_k.gguf filter=lfs diff=lfs merge=lfs -tex
 turkish-llama-3-8b-function-calling-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
 turkish-llama-3-8b-function-calling-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
 turkish-llama-3-8b-function-calling-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+turkish-llama-3-8b-function-calling.q2_k.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,5 @@
 ---
-base_model: atasoglu/Turkish-Llama-3-8B-function-calling
-datasets:
-- atasoglu/turkish-function-calling-20k
-language:
-- en
-- tr
-license: apache-2.0
-pipeline_tag: text-generation
+base_model: ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1
 tags:
 - text-generation-inference
 - transformers
@@ -14,76 +7,159 @@ tags:
 - llama
 - trl
 - sft
-- llama-cpp
-- matrixportal
----
-
-# oncu/Turkish-Llama-3-8B-function-calling-GGUF
-   This model was converted to GGUF format from [`atasoglu/Turkish-Llama-3-8B-function-calling`](https://huggingface.co/atasoglu/Turkish-Llama-3-8B-function-calling) using llama.cpp via the ggml.ai's [all-gguf-same-where](https://huggingface.co/spaces/matrixportal/all-gguf-same-where) space.
-Refer to the [original model card](https://huggingface.co/atasoglu/Turkish-Llama-3-8B-function-calling) for more details on the model.
-
-## ✅ Quantized Models Download List
-
-### 🔍 Recommended Quantizations
-- **✨ General CPU Use:** [`Q4_K_M`](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q4_k_m.gguf) (Best balance of speed/quality)
-- **📱 ARM Devices:** [`Q4_0`](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q4_0.gguf) (Optimized for ARM CPUs)
-- **🏆 Maximum Quality:** [`Q8_0`](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q8_0.gguf) (Near-original quality)
-
-### 📦 Full Quantization Options
-| 🚀 Download | 🔢 Type | 📝 Notes |
-|:---------|:-----|:------|
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q2_k.gguf) | ![Q2_K](https://img.shields.io/badge/Q2_K-1A73E8) | Basic quantization |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q3_k_s.gguf) | ![Q3_K_S](https://img.shields.io/badge/Q3_K_S-34A853) | Small size |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q3_k_m.gguf) | ![Q3_K_M](https://img.shields.io/badge/Q3_K_M-FBBC05) | Balanced quality |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q3_k_l.gguf) | ![Q3_K_L](https://img.shields.io/badge/Q3_K_L-4285F4) | Better quality |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q4_0.gguf) | ![Q4_0](https://img.shields.io/badge/Q4_0-EA4335) | Fast on ARM |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q4_k_s.gguf) | ![Q4_K_S](https://img.shields.io/badge/Q4_K_S-673AB7) | Fast, recommended |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q4_k_m.gguf) | ![Q4_K_M](https://img.shields.io/badge/Q4_K_M-673AB7) ⭐ | Best balance |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q5_0.gguf) | ![Q5_0](https://img.shields.io/badge/Q5_0-FF6D01) | Good quality |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q5_k_s.gguf) | ![Q5_K_S](https://img.shields.io/badge/Q5_K_S-0F9D58) | Balanced |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q5_k_m.gguf) | ![Q5_K_M](https://img.shields.io/badge/Q5_K_M-0F9D58) | High quality |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q6_k.gguf) | ![Q6_K](https://img.shields.io/badge/Q6_K-4285F4) 🏆 | Very good quality |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-q8_0.gguf) | ![Q8_0](https://img.shields.io/badge/Q8_0-EA4335) ⚡ | Fast, best quality |
-| [Download](https://huggingface.co/oncu/Turkish-Llama-3-8B-function-calling-GGUF/resolve/main/turkish-llama-3-8b-function-calling-f16.gguf) | ![F16](https://img.shields.io/badge/F16-000000) | Maximum accuracy |
-
-💡 **Tip:** Use `F16` for maximum precision when quality is critical
-
-
----
-# 🚀 Applications and Tools for Locally Quantized LLMs
-## 🖥️ Desktop Applications
-
-| Application     | Description                                                                                  | Download Link                                                                  |
-|-----------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
-| **Llama.cpp**   | A fast and efficient inference engine for GGUF models.                                       | [GitHub Repository](https://github.com/ggml-org/llama.cpp)                     |
-| **Ollama**      | A streamlined solution for running LLMs locally.                                             | [Website](https://ollama.com/)                                                 |
-| **AnythingLLM** | An AI-powered knowledge management tool.                                                     | [GitHub Repository](https://github.com/Mintplex-Labs/anything-llm)             |
-| **Open WebUI**  | A user-friendly web interface for running local LLMs.                                        | [GitHub Repository](https://github.com/open-webui/open-webui)                  |
-| **GPT4All**     | A user-friendly desktop application supporting various LLMs, compatible with GGUF models.    | [GitHub Repository](https://github.com/nomic-ai/gpt4all)                       |
-| **LM Studio**   | A desktop application designed to run and manage local LLMs, supporting GGUF format.         | [Website](https://lmstudio.ai/)                                                |
-| **GPT4All Chat**| A chat application compatible with GGUF models for local, offline interactions.              | [GitHub Repository](https://github.com/nomic-ai/gpt4all)                       |
-
----
-
-## 📱 Mobile Applications
-
-| Application       | Description                                                                                  | Download Link                                                                  |
-|-------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
-| **ChatterUI**     | A simple and lightweight LLM app for mobile devices.                                         | [GitHub Repository](https://github.com/Vali-98/ChatterUI)                      |
-| **Maid**          | Mobile Artificial Intelligence Distribution for running AI models on mobile devices.         | [GitHub Repository](https://github.com/Mobile-Artificial-Intelligence/maid)    |
-| **PocketPal AI**  | A mobile AI assistant powered by local models.                                               | [GitHub Repository](https://github.com/a-ghorbani/pocketpal-ai)                |
-| **Layla**         | A flexible platform for running various AI models on mobile devices.                         | [Website](https://www.layla-network.ai/)                                       |
-
----
-
-## 🎨 Image Generation Applications
-
-| Application                         | Description                                                                                  | Download Link                                                                  |
-|-------------------------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
-| **Stable Diffusion**                | An open-source AI model for generating images from text.                                     | [GitHub Repository](https://github.com/CompVis/stable-diffusion)               |
-| **Stable Diffusion WebUI**          | A web application providing access to Stable Diffusion models via a browser interface.       | [GitHub Repository](https://github.com/AUTOMATIC1111/stable-diffusion-webui)   |
-| **Local Dream**                     | Android Stable Diffusion with Snapdragon NPU acceleration. Also supports CPU inference.                                              | [GitHub Repository](https://github.com/xororz/local-dream)                     |
-| **Stable-Diffusion-Android (SDAI)** | An open-source AI art application for Android devices, enabling digital art creation.        | [GitHub Repository](https://github.com/ShiftHackZ/Stable-Diffusion-Android)    |
-
+license: apache-2.0
+language:
+- en
+- tr
+datasets:
+- atasoglu/turkish-function-calling-20k
+pipeline_tag: text-generation
 ---
 
+# Uploaded  model
+
+**This model was adapted from [ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1](https://huggingface.co/ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1) and fine-tuned on the [atasoglu/turkish-function-calling-20k](https://huggingface.co/datasets/atasoglu/turkish-function-calling-20k) dataset to perform function calling tasks in Turkish.**
+
+- **Developed by:** atasoglu
+- **License:** apache-2.0
+- **Finetuned from model :** ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1
+
+This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+# Usage
+
+First, load the model:
+
+```python
+import json
+from unsloth import FastLanguageModel
+
+# loading the model and tokenizer
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="atasoglu/Turkish-Llama-3-8B-function-calling",
+    load_in_4bit=True,
+)
+FastLanguageModel.for_inference(model)
+```
+
+Setup the tools and messages:
+
+```python
+# define the prompt templates
+system_prompt = """Sen yardımsever, akıllı ve fonksiyon çağrısı yapabilen bir asistansın.
+Aşağıda JSON parçası içinde verilen fonksiyonları kullanarak kullanıcının sorusunu uygun şekilde cevaplamanı istiyorum.
+
+Fonksiyon çağrısı yaparken uyman gereken talimatlar:
+
+* Fonksiyonlar, JSON şeması olarak ifade edilmiştir.
+* Eğer kullanıcının sorusu, bu fonksiyonlardan en az biri kullanılarak cevaplanabiliyorsa; uygun bir fonksiyon çağrısını JSON parçası içinde oluştur.
+* Fonksiyonların parametreleri için asla uydurmalar yapma ve sadece kullanıcının verdiği bilgileri kullan.
+* Eğer kullanıcının sorusu herhangi bir fonksiyon ile cevaplanamıyorsa, sadece "Verilen fonksiyonlarla cevaplanamaz" metnini döndür ve başka bir açıklama yapma.
+
+Bu talimatlara uyarak soruları cevaplandır."""
+
+user_prompt = """### Fonksiyonlar
+
+'''json
+{tools}
+'''
+
+### Soru
+
+{query}"""
+
+# define the tools and messages
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_weather",
+            "description": "Get current temperature for a given location.",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "City and country e.g. Bogotá, Colombia",
+                    }
+                },
+                "required": ["location"],
+                "additionalProperties": False,
+            },
+            "strict": True,
+        },
+    }
+]
+query = "Paris'te hava şu anda nasıl?"
+messages = [
+    {
+        "role": "system",
+        "content": system_prompt,
+    },
+    {
+        "role": "user",
+        "content": user_prompt.format(
+            tools=json.dumps(tools, ensure_ascii=False),
+            query=query,
+        ),
+    },
+]
+```
+
+**NOTE:** Change the *single quote* character to a *backtick* in the user prompt before running to specify the JSON snippet.
+
+Then, generate and evaluate the output:
+
+```python
+import re
+
+
+# define an evaluation function
+def eval_function_calling(text):
+    match_ = re.search(r"```json(.*)```", text, re.DOTALL)
+    if match_ is None:
+        return False, text
+    return True, json.loads(match_.group(1).strip())
+
+
+# tokenize the inputs
+inputs = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_dict=True,
+    return_tensors="pt",
+).to("cuda")
+
+# define generation arguments
+generation_kwargs = dict(
+    do_sample=True,
+    use_cache=True,
+    max_new_tokens=500,
+    temperature=0.3,
+    top_p=0.9,
+    top_k=40,
+)
+
+# finally, generate the output
+outputs = model.generate(**inputs, **generation_kwargs)
+output_ids = outputs[:, inputs["input_ids"].shape[1] :]
+generated_texts = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
+has_function_calling, results = eval_function_calling(generated_texts[0])
+
+# print the model response
+if has_function_calling:
+    for result in results:
+        fn = result["function"]
+        name, args = fn["name"], fn["arguments"]
+        print(f"Calling {name!r} function with these arguments: {args}")
+else:
+    print(f"No function call: {results!r}")
+```
+
+Output:
+
+```console
+Calling 'get_weather' function with these arguments: {"location":"Paris, France"}
+```

turkish-llama-3-8b-function-calling.q2_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bb8b5f18ec03d3ca183a3a55ae8a5ae5599c6eed2a549315f4d8dcaf8f9a0c3
+size 3179132352